English
Related papers

Related papers: Resurrecting saturated LLM benchmarks with adversa…

200 papers

Large Language Models (LLMs) excel at various tasks, including solving math word problems (MWPs), but struggle with real-world problems containing irrelevant information. To address this, we propose a prompting framework that generates…

Computation and Language · Computer Science 2025-09-17 Ujjwala Anantheswaran , Himanshu Gupta , Kevin Scaria , Shreyas Verma , Chitta Baral , Swaroop Mishra

Recent observations have underscored a disparity between the inflated benchmark scores and the actual performance of LLMs, raising concerns about potential contamination of evaluation benchmarks. This issue is especially critical for…

Computation and Language · Computer Science 2024-04-05 Chunyuan Deng , Yilun Zhao , Xiangru Tang , Mark Gerstein , Arman Cohan

Benchmarking outcomes increasingly govern trust, selection, and deployment of LLMs, yet these evaluations remain vulnerable to semantically equivalent adversarial perturbations. Prior work on adversarial robustness in NLP has emphasized…

Machine Learning · Computer Science 2025-10-16 Ivan Dubrovsky , Anastasia Orlova , Illarion Iov , Nina Gubina , Irena Gureeva , Alexey Zaytsev

Large Language Model (LLM) leaderboards based on benchmark rankings are regularly used to guide practitioners in model selection. Often, the published leaderboard rankings are taken at face value - we show this is a (potentially costly)…

Large language models (LLMs) regularly demonstrate new and impressive performance on a wide range of language, knowledge, and reasoning benchmarks. Such rapid progress has led many commentators to argue that LLM general cognitive…

Computation and Language · Computer Science 2025-02-21 James Fodor

Existing benchmarks are becoming saturated and struggle to separate model performances due to factors like data contamination and advancing LLM capabilities. This paper introduces EMDM (Enhanced Model Differentiation Metric), a novel…

Unlearning methods have the potential to improve the privacy and safety of large language models (LLMs) by removing sensitive or harmful information post hoc. The LLM unlearning research community has increasingly turned toward empirical…

Computation and Language · Computer Science 2025-04-09 Pratiksha Thaker , Shengyuan Hu , Neil Kale , Yash Maurya , Zhiwei Steven Wu , Virginia Smith

Widely used language-model benchmarks are increasingly saturated, with frontier systems often receiving near-tied scores that standard metrics cannot resolve. Rather than constructing harder alternatives, we ask whether existing tasks can…

Computation and Language · Computer Science 2026-05-29 Jiamin Chen , Yidi Wu , Qiexiang Wang , Qianben Chen , Yuchen Li , Yansen Zhang , Xiaokun Zhang , Wangchunshu Zhou , Chen Ma

As large language models (LLMs) are increasingly deployed in multi-turn dialogue and other sustained interactive scenarios, it is essential to understand how extended context affects their performance. Popular benchmarks, focusing primarily…

Computation and Language · Computer Science 2025-06-03 Robert Hankache , Kingsley Nketia Acheampong , Liang Song , Marek Brynda , Raad Khraishi , Greig A. Cowan

Large language models (LLMs) are stochastic, and not all models give deterministic answers, even when setting temperature to zero with a fixed random seed. However, few benchmark studies attempt to quantify uncertainty, partly due to the…

Computation and Language · Computer Science 2025-06-30 Robert E. Blackwell , Jon Barry , Anthony G. Cohn

We introduce WiCkeD, a simple method to increase the complexity of existing multiple-choice benchmarks by randomly replacing a choice with "None of the above", a method often used in educational tests. We show that WiCkeD can be…

Computation and Language · Computer Science 2025-02-26 Ahmed Elhady , Eneko Agirre , Mikel Artetxe

The versatility of large language models (LLMs) led to the creation of diverse benchmarks that thoroughly test a variety of language models' abilities. These benchmarks consist of tens of thousands of examples making evaluation of LLMs very…

Computation and Language · Computer Science 2024-05-28 Felipe Maia Polo , Lucas Weber , Leshem Choshen , Yuekai Sun , Gongjun Xu , Mikhail Yurochkin

This study investigates whether repeating questions within prompts influences the performance of large language models (LLMs). We hypothesize that reiterating a question within a single prompt might enhance the model's focus on key elements…

Computation and Language · Computer Science 2025-03-13 Sagi Shaier , Mario Sanz-Guerrero , Katharina von der Wense

The increasing complexity of large language models (LLMs) raises concerns about their ability to "cheat" on standard Question Answering (QA) benchmarks by memorizing task-specific data. This undermines the validity of benchmark evaluations,…

Computation and Language · Computer Science 2025-09-16 Yixiong Fang , Tianran Sun , Yuling Shi , Min Wang , Xiaodong Gu

Large Language Models (LLMs) effectiveness is usually evaluated by means of benchmarks such as MMLU, ARC-C, or HellaSwag, where questions are presented in their original wording, thus in a fixed, standardized format. However, real-world…

Computation and Language · Computer Science 2025-09-05 Riccardo Lunardi , Vincenzo Della Mea , Stefano Mizzaro , Kevin Roitero

Large Language Models (LLMs) demonstrate significant potential in multi-agent negotiation tasks, yet evaluation in this domain remains challenging due to a lack of robust and generalizable benchmarks. Abdelnabi et al. (2024) introduce a…

Machine Learning · Computer Science 2026-02-24 Jorge Carrasco Pollo , Ioannis Kapetangeorgis , Joshua Rosenthal , John Hua Yao

Novel reinforcement learning algorithms, or improvements on existing ones, are commonly justified by evaluating their performance on benchmark environments and are compared to an ever-changing set of standard algorithms. However, despite…

Machine Learning · Computer Science 2024-06-25 Scott M. Jordan , Adam White , Bruno Castro da Silva , Martha White , Philip S. Thomas

Large Language Models (LLMs) deliver strong performance but incur high inference cost in real-world services, especially under workloads with repeated or near-duplicate queries across users and sessions. In this work, we propose MemBoost, a…

Computation and Language · Computer Science 2026-03-30 Joris Köster , Zixuan Liu , Siavash Khajavi , Zizhan Zheng

The pursuit of leaderboard rankings in Large Language Models (LLMs) has created a fundamental paradox: models excel at standardized tests while failing to demonstrate genuine language understanding and adaptability. Our systematic analysis…

Computation and Language · Computer Science 2024-12-06 Sourav Banerjee , Ayushi Agarwal , Eishkaran Singh

The training process of large language models (LLMs) often involves varying degrees of test data contamination. Although current LLMs are achieving increasingly better performance on various benchmarks, their performance in practical…

Computation and Language · Computer Science 2024-06-25 Qin Zhu , Qingyuan Cheng , Runyu Peng , Xiaonan Li , Tengxiao Liu , Ru Peng , Xipeng Qiu , Xuanjing Huang
‹ Prev 1 2 3 10 Next ›